Number of found records: 40
|
CONROY, John M.; OKUROWSKI, Mary Ellen; OLEARY, Dianne P.; SCHLESINGER, Judith D. |
|
Machine and human performance for single and multidocument summarization. |
|
IEEE-Intelligent-System, 2003, vol.18, n.1, pp.46-54. |
|
On line (11/05/2005) |
|
Surveys modern summarization techniques and their evaluations at the 2002 Document Understanding Conference (DUC 2002). The DUC 2002 evaluation revealed numerous language processing challenges that impact textsummarization. Examines the techniques used in a multidocument summarization system the authors developed and its performance at DUC 2002 and also discusses the need for regularization of human summaries. (AU) |
|
Automatic abstracting; Artificial intelligence; Evaluation |
Assessment |
|
|
|
|
CRAVEN, Timothy C. |
|
Human creation of abstracts with selected computer assistance tools |
|
Information Research, 1998, vol.3, n.4 |
|
On line ( 15/06/2004) |
|
After introductory training, a research assistant used the TEXNET abstracting assistance software to create abstracts to articles available via the World Wide Web. The assistant also complied introductory documentation, including a guide to abstracting using computer assistance tools. This article discusses problems encountered, tools selected for preferred use, and implications for future software development. (AU) |
|
TEXNET; abstracting assistance software; automatic abstracting; WWW |
Assessment |
|
|
|
|
CRAVEN, Timothy C. |
|
'DESCRIPTION' META tags in locally linked web pages |
|
Aslib-Proceedings, 2001, vol. 53, n. 6, p.203-16 |
|
On line (11/05/2005) |
|
As part of the author's research aimed at developing a prototype computerized abstractor's assistant, reports on work that investigated how people and organizations summarize their own web pages, and, specifically, how and to what extent they make use of META tags, especially those with NAME = DESCRIPTION, for this purpose. Surveys advice given in printed and web-based sources on HTML META tags with NAME = DESCRIPTION. In order to determine patterns of relationships among descriptions on the same site, links were followed automatically from 460 pages registered with Yahoo! and previously found to contain descriptions. Results showed that sites where the registered page pointed to many other pages were significantly less likely to reuse the same description on those other pages; and where different descriptions were used, words from the registered page's description tended to appear toward the beginning of other descriptions. (DB) |
|
Automatic abstracting; World Wide Web; Web pages; Metadata; Tagging; HTML |
Assessment |
|
|
|
|
CRAVEN, Timothy C. |
|
A thesaurus for use in a computer-aided abstracting tool kit |
|
Proceedings of the 56th Annual Meeting of the American Society for Information Science, Columbus, Ohio, 24-28 October 1993. Edited by Susan Bonzi, Medford, New Jersey, Learned Information, Inc., For American Society for Information Science, 1993, p.178-84. |
|
PDF |
|
A multi-purpose thesaurus is among abstracting assistance features being prototyped in the TEXNET text network management system. The thesaurus is intended to support vocabulary control, including production of a variety of printed thesaurus displays, as well as automatic weighting of passages and Roget-style suggestion of alternate terms. (DB) |
|
Automatic abstracting; Thesauri; TEXNET |
Assessment |
|
|
|
|
